Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling
Jiancheng Yang,Qiang Zhang,Bingbing Ni,Linguo Li,Jinxian Liu,Mengdie Zhou,Qi Tian +6 more
- 01 Jun 2019
- pp 3323-3332
530
TL;DR: This work develops Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention, and proposes an end-to-end learnable and task-agnostic sampling operation, named Gumbel Subset Sampling (GSS), to select a representative subset of input points.
read more
Abstract: Geometric deep learning is increasingly important thanks to the popularity of 3D sensors. Inspired by the recent advances in NLP domain, the self-attention transformer is introduced to consume the point clouds. We develop Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention. We demonstrate its ability to process size-varying inputs, and prove its permutation equivariance. Besides, prior work uses heuristics dependence on the input data (e.g., Furthest Point Sampling) to hierarchically select subsets of input points. Thereby, we for the first time propose an end-to-end learnable and task-agnostic sampling operation, named Gumbel Subset Sampling (GSS), to select a representative subset of input points. Equipped with Gumbel-Softmax, it produces a "soft" continuous subset in training phase, and a "hard" discrete subset in test phase. By selecting representative subsets in a hierarchical fashion, the networks learn a stronger representation of the input sets with lower computation cost. Experiments on classification and segmentation benchmarks show the effectiveness and efficiency of our methods. Furthermore, we propose a novel application, to process event camera stream as point clouds, and achieve a state-of-the-art performance on DVS128 Gesture Dataset.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
Jingyu Gong,Jiachen Xu,Xin Tan,Jie Zhou,Yanyun Qu,Yuan Xie,Lizhuang Ma +6 more
TL;DR: This paper proposes a boundary-aware geometric encoding method for 3D point cloud segmentation, incorporating a boundary prediction module and geometric convolution operation to improve feature extraction and aggregation, achieving state-of-the-art performance on ScanNet v2 and S3DIS benchmarks.
Geometry Guided Network for Point Cloud Registration
Taewon Min,Eunseok Kim,Inwook Shim +2 more
- 14 Jul 2021
TL;DR: Geometry guided point cloud registration (G $^2$ Net) as discussed by the authors uses spherical positional encoding and geometry consistency loss to learn globally unique point features by assigning global geometric positional information into irregular 3D points.
Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds Using Spatial-Aware Capsules
TL;DR: A novel deep learning network for aggregating features and spatial relationships of local regions on point clouds, which aims to learn more discriminative shape representation and outperforms the state-of-the-art methods in the 3D shape classification, retrieval and segmentation tasks under the well-known ModelNet and ShapeNet datasets.
Robust Geometry-Dependent Attack for 3D Point Clouds
TL;DR: A novel Geometry-Dependent Attack (GDA), which aims to generate more robust adversarial point clouds with lower perturbation costs by capturing and preserving the geometry-guided topology information.
The Applications of 3D Input Data and Scalability Element by Transformer Based Methods: A Review
Abubakar Sulaiman Gezawa,Chibiao Liu,Naveed Ur Rehman Junejo,Haruna Chiroma +3 more
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
•Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
- 12 Jun 2017
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
•Posted Content
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
82.5K
•Posted Content
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
81.7K